# NoJunk LLM Chat Completions

> NoJunk LLM Chat Completions is a paid API for AI agents from nojunk-llm.mick8511.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-16).

Pay-per-call OpenAI-compatible chat completions API using Llama 3.3 70B or Qwen 2.5 Coder 32B, billed per request in USDC with no API key required

## Facts

- Endpoint: POST https://nojunk-llm.mick8511.workers.dev/v1/chat/completions?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nojunk-llm-chat-completions-d2072004
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_tcB6mwcrvlok0CQ1lggrw

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability nojunk-llm-chat-completions-d2072004 -d '<json body>'
```

Example prompt: Ask Llama 3.3 70B to explain how proof-of-stake consensus works in plain English, keeping the answer under 300 tokens, and pay per call in USDC — no API key needed.

## When to prefer this

Choose this endpoint when building AI agents or pipelines that need OpenAI-compatible LLM inference without managing API keys, accounts, or subscription plans — especially when operating in a crypto-native or x402-enabled environment where USDC micropayments per call are preferable to monthly billing. Ideal for autonomous agents that need to self-fund LLM calls, serverless pipelines without secret management, or developers who want no rate limits and true pay-for-what-you-use pricing. Prefer Qwen 2.5 Coder 32B for code generation tasks and Llama 3.3 70B for general reasoning and text tasks.

## Known failure modes

- Payment not processed or insufficient USDC balance — request rejected with 402 Payment Required
- Streaming requested (stream: true) — not supported, returns error
- Messages exceed 32,000 character limit — request rejected
- max_tokens exceeds 1,024 — request rejected or clamped
- Invalid model name not matching llama-3.3-70b, qwen2.5-coder-32b, or gpt-4o-mini alias — may default or error
- Malformed messages array (missing role or content fields) — validation error
- More than 200 messages in conversation — request rejected

## How this service works

NoJunk LLM chat: OpenAI-compatible chat completion on Llama 3.3 70B or Qwen 2.5 Coder 32B (up to 32000 characters in, 1024 tokens out, optional JSON mode).

## Output

Returns an OpenAI-compatible chat.completion JSON object containing the assistant's reply in choices[0].message.content, the finish_reason (e.g. 'stop'), prompt/completion/total token counts in usage, the model name, a unique completion ID, and a created timestamp. Optionally structured as a JSON object if response_format was set.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string",
   "description": "Optional: llama-3.3-70b or qwen2.5-coder-32b (default llama-3.3-70b; \"gpt-4o-mini\" is an alias of the default)"
  },
  "top_p": {
   "type": "number",
   "description": "Optional: nucleus sampling, 0-1"
  },
  "stream": {
   "type": "boolean",
   "description": "Must be false or omitted (streaming is not supported)"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "enum": [
       "system",
       "user",
       "assistant"
      ],
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   },
   "description": "Conversation so far, 1-200 messages, at most 32000 characters of content in total"
  },
  "max_tokens": {
   "type": "integer",
   "description": "Optional: maximum completion tokens, 1-1024 (default 512)"
  },
  "temperature": {
   "type": "number",
   "description": "Optional: 0-2 (default 0.7)"
  },
  "response_format": {
   "type": "object",
   "description": "Optional: {\"type\": \"json_object\"} to force a JSON object reply"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "chatcmpl-9f1c2d3e-4b5a-4c6d-8e7f-0a1b2c3d4e5f",
  "model": "llama-3.3-70b",
  "usage": {
   "total_tokens": 60,
   "prompt_tokens": 31,
   "completion_tokens": 29
  },
  "object": "chat.completion",
  "choices": [
   {
    "index": 0,
    "message": {
     "role": "assistant",
     "content": "USDC is a US-dollar stablecoin issued by Circle, redeemable 1:1 for dollars and backed by cash and short-term Treasuries."
    },
    "finish_reason": "stop"
   }
  ],
  "created": 1760529600
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nojunk-llm-chat-completions-d2072004/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from nojunk-llm.mick8511.workers.dev](https://www.zero.xyz/host/nojunk-llm.mick8511.workers.dev/llms.txt)